Knee joint angle prediction method and system based on electromyographic signals and angle signals

The invention relates to a knee joint angle prediction method based on electromyographic signals and angle signals. A human body lower limb motion information acquisition unit and acquisition hardware, an experimental platform and test unit, a signal preprocessing and feature extraction unit and a machine learning system training and testing unit are integrally designed; the human body lower limbmotion information acquisition unit and acquisition hardware extract human body rectus femoris and biceps femoris electromyographic signals and hip joint and knee joint angle signals; the experiment platform and test unit are worn on the human body and are connected with the human body lower limb motion information acquisition unit and a notebook computer through interfaces; the signal preprocessing and feature extraction unit is used for carrying out preprocessing and feature extraction on the acquired electromyographic signals and angle signals, eliminating signal noises and extracting signal features; and the machi